attribute.java

本程序用于对页面信息进行提取并分析

     * This is usually just an equals sign, but in poorly formed attributes it
     * can include whitespace on either or both sides of an equals sign.
     * @return The assignment string.
     * @see #setAssignment
     */
    public String getAssignment ()
    {
        return (mAssignment);
    }

    /**
     * Get the assignment string of this attribute.
     * @param buffer The buffer to place the assignment string in.
     * @see #getAssignment()
     * @see #setAssignment
     */
    public void getAssignment (StringBuffer buffer)
    {
        if (null != mAssignment)
            buffer.append (mAssignment);
    }

    /**
     * Set the assignment string of this attribute.
     * <em>WARNING:</em> Setting this property to other than an equals sign
     * or <code>null</code> will result in malformed HTML. In the case of a
     * <code>null</code>, the {@link  #setValue value} should also be set to
     * <code>null</code>.
     * @param assignment The new assignment string.
     * @see #getAssignment
     * @see #getAssignment(StringBuffer)
     */
    public void setAssignment (String assignment)
    {
        mAssignment = assignment;
    }

    /**
     * Get the value of the attribute.
     * The part after the equals sign, or the text if it's just a whitepace
     * 'attribute'.
     * <em>NOTE:</em> This does not include any quotes that may have enclosed
     * the value when it was read. To get the un-stripped value use
     * {@link  #getRawValue}.
     * @return The value, or <code>null</code> if it's a stand-alone or
     * empty attribute, or the text if it's just a whitepace 'attribute'.
     * @see #setValue
     */
    public String getValue ()
    {
        return (mValue);
    }

    /**
     * Get the value of the attribute.
     * @param buffer The buffer to place the value in.
     * @see #getValue()
     * @see #setValue
     */
    public void getValue (StringBuffer buffer)
    {
        if (null != mValue)
            buffer.append (mValue);
    }

    /**
     * Set the value of the attribute.
     * The part after the equals sign, or the text if it's a whitepace
     * 'attribute'.
     * <em>WARNING:</em> Setting this property to a value that needs to be
     * quoted without also setting the quote character will result in malformed
     * HTML.
     * @param value The new value.
     * @see #getValue
     * @see #getValue(StringBuffer)
     */
    public void setValue (String value)
    {
        mValue = value;
    }

    /**
     * Get the quote, if any, surrounding the value of the attribute, if any.
     * @return Either ' or " if the attribute value was quoted, or zero
     * if there are no quotes around it.
     * @see #setQuote
     */
    public char getQuote ()
    {
        return (mQuote);
    }

    /**
     * Get the quote, if any, surrounding the value of the attribute, if any.
     * @param buffer The buffer to place the quote in.
     * @see #getQuote()
     * @see #setQuote
     */
    public void getQuote (StringBuffer buffer)
    {
        if (0 != mQuote)
            buffer.append (mQuote);
    }

    /**
     * Set the quote surrounding the value of the attribute.
     * <em>WARNING:</em> Setting this property to zero will result in malformed
     * HTML if the {@link  #getValue value} needs to be quoted (i.e. contains
     * whitespace).
     * @param quote The new quote value.
     * @see #getQuote
     * @see #getQuote(StringBuffer)
     */
    public void setQuote (char quote)
    {
        mQuote = quote;
    }

    /**
     * Get the raw value of the attribute.
     * The part after the equals sign, or the text if it's just a whitepace
     * 'attribute'. This includes the quotes around the value if any.
     * @return The value, or <code>null</code> if it's a stand-alone attribute,
     * or the text if it's just a whitepace 'attribute'.
     * @see #setRawValue
     */
    public String getRawValue ()
    {
        char quote;
        StringBuffer buffer;
        String ret;

        if (isValued ())
        {
            quote = getQuote ();
            if (0 != quote)
            {
                buffer = new StringBuffer (); // todo: what is the value length?
                buffer.append (quote);
                getValue (buffer);
                buffer.append (quote);
                ret = buffer.toString ();
            }
            else
                ret = getValue ();
        }
        else
            ret = null;

        return (ret);
    }

    /**
     * Get the raw value of the attribute.
     * The part after the equals sign, or the text if it's just a whitepace
     * 'attribute'. This includes the quotes around the value if any.
     * @param buffer The string buffer to append the attribute value to.
     * @see #getRawValue()
     * @see #setRawValue
     */
    public void getRawValue (StringBuffer buffer)
    {
        getQuote (buffer);
        getValue (buffer);
        getQuote (buffer);
    }

    /**
     * Set the value of the attribute and the quote character.
     * If the value is pure whitespace, assign it 'as is' and reset the
     * quote character. If not, check for leading and trailing double or
     * single quotes, and if found use this as the quote character and
     * the inner contents of <code>value</code> as the real value.
     * Otherwise, examine the string to determine if quotes are needed
     * and an appropriate quote character if so. This may involve changing
     * double quotes within the string to character references.
     * @param value The new value.
     * @see #getRawValue
     * @see #getRawValue(StringBuffer)
     */
    public void setRawValue (String value)
    {
        char ch;
        boolean needed;
        boolean singleq;
        boolean doubleq;
        String ref;
        StringBuffer buffer;
        char quote;

        quote = 0;
        if ((null != value) && (0 != value.trim ().length ()))
        {
            if (value.startsWith ("'") && value.endsWith ("'")
                && (2 <= value.length ()))
            {
                quote = '\'';
                value = value.substring (1, value.length () - 1);
            }
            else if (value.startsWith ("\"") && value.endsWith ("\"")
                && (2 <= value.length ()))
            {
                quote = '"';
                value = value.substring (1, value.length () - 1);
            }
            else
            {
                // first determine if there's whitespace in the value
                // and while we're at it find a suitable quote character
                needed = false;
                singleq = true;
                doubleq = true;
                for (int i = 0; i < value.length (); i++)
                {
                    ch = value.charAt (i);
                    if ('\'' == ch)
                    {
                        singleq  = false;
                        needed = true;
                    }
                    else if ('"' == ch)
                    {
                        doubleq = false;
                        needed = true;
                    }
                    else if (!('-' == ch) && !('.' == ch) && !('_' == ch)
                       && !(':' == ch) && !Character.isLetterOrDigit (ch))
                    {
                        needed = true;
                    }
                }

                // now apply quoting
                if (needed)
                {
                    if (doubleq)
                        quote = '"';
                    else if (singleq)
                        quote = '\'';
                    else
                    {
                        // uh-oh, we need to convert some quotes into character
                        // references, so convert all double quotes into &#34;
                        quote = '"';
                        ref = "&quot;"; // Translate.encode (quote);
                        // JDK 1.4: value = value.replaceAll ("\"", ref);
                        buffer = new StringBuffer (
                                value.length() * (ref.length () - 1));
                        for (int i = 0; i < value.length (); i++)
                        {
                            ch = value.charAt (i);
                            if (quote == ch)
                                buffer.append (ref);
                            else
                                buffer.append (ch);
                        }
                        value = buffer.toString ();
                    }
                }
            }
        }
        setValue (value);
        setQuote (quote);
    }

    /**
     * Predicate to determine if this attribute is whitespace.
     * @return <code>true</code> if this attribute is whitespace,
     * <code>false</code> if it is a real attribute.
     */
    public boolean isWhitespace ()
    {
        return (null == getName ());
    }

    /**
     * Predicate to determine if this attribute has no equals sign (or value).
     * @return <code>true</code> if this attribute is a standalone attribute.
     * <code>false</code> if has an equals sign.
     */
    public boolean isStandAlone ()
    {
        return ((null != getName ()) && (null == getAssignment ()));
    }

    /**
     * Predicate to determine if this attribute has an equals sign but no value.
     * @return <code>true</code> if this attribute is an empty attribute.
     * <code>false</code> if has an equals sign and a value.
     */
    public boolean isEmpty ()
    {
        return ((null != getAssignment ()) && (null == getValue ()));
    }

    /**
     * Predicate to determine if this attribute has a value.
     * @return <code>true</code> if this attribute has a value.
     * <code>false</code> if it is empty or standalone.
     */
    public boolean isValued ()
    {
        return (null != getValue ());
    }

    /**
     * Get the length of the string value of this attribute.
     * @return The number of characters required to express this attribute.
     */
    public int getLength ()
    {
        String name;
        String assignment;
        String value;
        char quote;
        int ret;

        ret = 0;
        name = getName ();
        if (null != name)
            ret += name.length ();
        assignment = getAssignment ();
        if (null != assignment)
            ret += assignment.length ();
        value = getValue ();
        if (null != value)
            ret += value.length ();
        quote = getQuote ();
        if (0 != quote)
            ret += 2;

        return (ret);
    }

    /**
     * Get a text representation of this attribute.
     * Suitable for insertion into a tag, the output is one of
     * the forms:
     * <code>
     * <pre>
     * value
     * name
     * name=
     * name=value
     * name='value'
     * name="value"
     * </pre>
     * </code>
     * @return A string that can be used within a tag.
     */
    public String toString ()
    {
        int length;
        StringBuffer ret;

        // get the size to avoid extra StringBuffer allocations
        length = getLength ();
        ret = new StringBuffer (length);
        toString (ret);

        return (ret.toString ());
    }

    /**
     * Get a text representation of this attribute.
     * @param buffer The accumulator for placing the text into.
     * @see #toString()
     */
    public void toString (StringBuffer buffer)
    {
        getName (buffer);
        getAssignment (buffer);
        getRawValue (buffer);
    }

}